On monotone optimal decision rules and the stay-on-a-winner rule for the two-armed bandit

DOI10.1007/BF01897828zbMath0616.90093MaRDI QIDQ1821704

H. Benzing, Michael Kolonko

Publication date: 1985

Published in: Metrika (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/176018

zbMATH Keywords

two-armed banditexistence of monotone optimal decision rulesstay-on-a-winner rules

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items

Increasing Lipschitz continuous maximizers of some dynamic programs ⋮ Monotone optimal decision rules and their computation

Cites Work

• Unnamed Item
• Unnamed Item
• On the k-armed Bernoulli bandit: monotonicity of the total reward under an arbitrary prior distribution
• On Sequential Designs for Maximizing the Sum of $n$ Observations
• On the Bernoulli two-armed bandit problem
• Minimizing a Submodular Function on a Lattice
• A note on ‘monotone optimal policies for markov decision processes’
• A note on structural properties of the Bernoulli two-armed bandit problem
• Some Concepts of Dependence
• A Bernoulli Two-armed Bandit